Hugging Face's logo

AlekseyKorshuk
/
6.7b-dalio-book-handwritten-io-constant-1e-6

Text Generation
Transformers
PyTorch
opt
Generated from Trainer
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Community
AlekseyKorshuk commited on
Commit
b27f3cc
•
1 Parent(s): 1390fc0

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +166 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.499117170061384,
4
+ "train_runtime": 11859.1153,
5
+ "train_samples": 442,
6
+ "train_samples_per_second": 0.037,
7
+ "train_steps_per_second": 0.005
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.499117170061384,
4
+ "train_runtime": 11859.1153,
5
+ "train_samples": 442,
6
+ "train_samples_per_second": 0.037,
7
+ "train_steps_per_second": 0.005
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 56,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 1e-06,
13
+ "loss": 2.5647,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.11,
18
+ "learning_rate": 1e-06,
19
+ "loss": 2.6396,
20
+ "step": 6
21
+ },
22
+ {
23
+ "epoch": 0.11,
24
+ "eval_accuracy": 0.29888098278902875,
25
+ "eval_loss": 2.50390625,
26
+ "eval_runtime": 65.6756,
27
+ "eval_samples_per_second": 4.796,
28
+ "eval_steps_per_second": 0.609,
29
+ "step": 6
30
+ },
31
+ {
32
+ "epoch": 0.21,
33
+ "learning_rate": 1e-06,
34
+ "loss": 2.5754,
35
+ "step": 12
36
+ },
37
+ {
38
+ "epoch": 0.21,
39
+ "eval_accuracy": 0.29990877577084474,
40
+ "eval_loss": 2.490234375,
41
+ "eval_runtime": 66.3232,
42
+ "eval_samples_per_second": 4.749,
43
+ "eval_steps_per_second": 0.603,
44
+ "step": 12
45
+ },
46
+ {
47
+ "epoch": 0.32,
48
+ "learning_rate": 1e-06,
49
+ "loss": 2.5859,
50
+ "step": 18
51
+ },
52
+ {
53
+ "epoch": 0.32,
54
+ "eval_accuracy": 0.3017940765067202,
55
+ "eval_loss": 2.46484375,
56
+ "eval_runtime": 66.3622,
57
+ "eval_samples_per_second": 4.747,
58
+ "eval_steps_per_second": 0.603,
59
+ "step": 18
60
+ },
61
+ {
62
+ "epoch": 0.43,
63
+ "learning_rate": 1e-06,
64
+ "loss": 2.5432,
65
+ "step": 24
66
+ },
67
+ {
68
+ "epoch": 0.43,
69
+ "eval_accuracy": 0.30347868393845406,
70
+ "eval_loss": 2.443359375,
71
+ "eval_runtime": 66.0194,
72
+ "eval_samples_per_second": 4.771,
73
+ "eval_steps_per_second": 0.606,
74
+ "step": 24
75
+ },
76
+ {
77
+ "epoch": 0.54,
78
+ "learning_rate": 1e-06,
79
+ "loss": 2.472,
80
+ "step": 30
81
+ },
82
+ {
83
+ "epoch": 0.54,
84
+ "eval_accuracy": 0.3053031685215593,
85
+ "eval_loss": 2.423828125,
86
+ "eval_runtime": 66.3343,
87
+ "eval_samples_per_second": 4.749,
88
+ "eval_steps_per_second": 0.603,
89
+ "step": 30
90
+ },
91
+ {
92
+ "epoch": 0.64,
93
+ "learning_rate": 1e-06,
94
+ "loss": 2.5184,
95
+ "step": 36
96
+ },
97
+ {
98
+ "epoch": 0.64,
99
+ "eval_accuracy": 0.3064465121936386,
100
+ "eval_loss": 2.408203125,
101
+ "eval_runtime": 66.2869,
102
+ "eval_samples_per_second": 4.752,
103
+ "eval_steps_per_second": 0.603,
104
+ "step": 36
105
+ },
106
+ {
107
+ "epoch": 0.75,
108
+ "learning_rate": 1e-06,
109
+ "loss": 2.4524,
110
+ "step": 42
111
+ },
112
+ {
113
+ "epoch": 0.75,
114
+ "eval_accuracy": 0.30782703886152163,
115
+ "eval_loss": 2.392578125,
116
+ "eval_runtime": 66.3104,
117
+ "eval_samples_per_second": 4.75,
118
+ "eval_steps_per_second": 0.603,
119
+ "step": 42
120
+ },
121
+ {
122
+ "epoch": 0.86,
123
+ "learning_rate": 1e-06,
124
+ "loss": 2.3876,
125
+ "step": 48
126
+ },
127
+ {
128
+ "epoch": 0.86,
129
+ "eval_accuracy": 0.30921364714468164,
130
+ "eval_loss": 2.37890625,
131
+ "eval_runtime": 66.2891,
132
+ "eval_samples_per_second": 4.752,
133
+ "eval_steps_per_second": 0.603,
134
+ "step": 48
135
+ },
136
+ {
137
+ "epoch": 0.96,
138
+ "learning_rate": 1e-06,
139
+ "loss": 2.4456,
140
+ "step": 54
141
+ },
142
+ {
143
+ "epoch": 0.96,
144
+ "eval_accuracy": 0.3103083378945448,
145
+ "eval_loss": 2.36328125,
146
+ "eval_runtime": 66.3214,
147
+ "eval_samples_per_second": 4.75,
148
+ "eval_steps_per_second": 0.603,
149
+ "step": 54
150
+ },
151
+ {
152
+ "epoch": 1.0,
153
+ "step": 56,
154
+ "total_flos": 3701894676480.0,
155
+ "train_loss": 2.499117170061384,
156
+ "train_runtime": 11859.1153,
157
+ "train_samples_per_second": 0.037,
158
+ "train_steps_per_second": 0.005
159
+ }
160
+ ],
161
+ "max_steps": 56,
162
+ "num_train_epochs": 1,
163
+ "total_flos": 3701894676480.0,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }